Re: [PATCH v9 19/41] btrfs: redirty released extent buffers in ZONED mode

[Johannes Thumshirn <Johannes.Thumshirn@wdc.com>]

On 03/11/2020 15:43, Josef Bacik wrote:
> This is a lot of work when you could just add
> 
> if (btrfs_is_zoned(fs_info))
> 	return;
> 
> to btrfs_clean_tree_block().  The dirty secret is we don't actually unset the 
> bits in the transaction io tree because it would require memory allocation 
> sometimes, so you don't even need to mess with ->dirty_pages in the first place. 
>   The only thing you need is to keep from clearing the EB dirty.  In fact you 
> could just do
> 
> if (btrfs_is_zoned(fs_info)) {
> 	memzero_extent_buffer(eb, 0, eb->len);
> 	set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
> }
> 
> to btrfs_clean_tree_block() and then in btrfs_free_tree_block() make sure we 
> always pin the extent if we're zoned.  Thanks,

As much as I'd love the simple solution you described it unfortunately didn't work
in our testing [1]. So unless I did something completely stupid [2] (which always
is an option) I don't think we can go with the easy solution here, unfortunately.

[1]
btrfs/001       [   16.212869] BTRFS error (device nullb1): unable to find ref byte nr 805388288 parent 805388288 root 5  owner 0 offset 0
[   16.214314] BTRFS: error (device nullb1) in __btrfs_free_extent:3196: errno=-2 No such entry
[   16.215270] BTRFS: error (device nullb1) in btrfs_run_delayed_refs:2215: errno=-2 No such entry                                                                                    
[   16.266987] BTRFS error (device nullb1): unable to find ref byte nr 805388288 parent 805388288 root 5  owner 0 offset 0                                
[   16.268788] BTRFS: error (device nullb1) in __btrfs_free_extent:3196: errno=-2 No such entry                                           
[   16.269973] BTRFS: error (device nullb1) in btrfs_run_delayed_refs:2215: errno=-2 No such entry
[   16.271210] BTRFS: error (device nullb1) in cleanup_transaction:1904: errno=-2 No such entry                                                  
[   16.297358] BTRFS error (device nullb1): unable to find ref byte nr 805502976 parent 805502976 root 1  owner 0 offset 0                       
[   16.299128] BTRFS: error (device nullb1) in __btrfs_free_extent:3196: errno=-2 No such entry   
[   16.300324] BTRFS: error (device nullb1) in btrfs_run_delayed_refs:2215: errno=-2 No such entry
[   16.335600] BTRFS error (device nullb1): unable to find ref byte nr 805388288 parent 805388288 root 5  owner 0 offset 0
[   16.337600] BTRFS: error (device nullb1) in __btrfs_free_extent:3196: errno=-2 No such entry
[   16.338785] BTRFS: error (device nullb1) in btrfs_run_delayed_refs:2215: errno=-2 No such entry                                                                                    
[   16.340026] BTRFS: error (device nullb1) in cleanup_transaction:1904: errno=-2 No such entry            
[   16.366461] BTRFS error (device nullb0): unable to find ref byte nr 805502976 parent 805502976 root 1  owner 0 offset 0
[   16.368304] BTRFS: error (device nullb0) in __btrfs_free_extent:3196: errno=-2 No such entry
[   16.369480] BTRFS: error (device nullb0) in btrfs_run_delayed_refs:2215: errno=-2 No such entry
[   16.370689] BTRFS: error (device nullb0) in cleanup_transaction:1904: errno=-2 No such entry
[   16.392890] BTRFS error (device nullb1): unable to find ref byte nr 805388288 parent 805388288 root 5  owner 0 offset 0
[   16.394531] BTRFS: error (device nullb1) in __btrfs_free_extent:3196: errno=-2 No such entry
[   16.395612] BTRFS: error (device nullb1) in btrfs_run_delayed_refs:2215: errno=-2 No such entry                                                        
[   16.396648] BTRFS: error (device nullb1) in cleanup_transaction:1904: errno=-2 No such entry
[   16.422315] BTRFS error (device nullb1): unable to find ref byte nr 805502976 parent 805502976 root 1  owner 0 offset 0                
[   16.424147] BTRFS: error (device nullb1) in __btrfs_free_extent:3196: errno=-2 No such entry
[   16.425320] BTRFS: error (device nullb1) in btrfs_run_delayed_refs:2215: errno=-2 No such entry
[   16.426532] BTRFS: error (device nullb1) in cleanup_transaction:1904: errno=-2 No such entry
_check_dmesg: something found in dmesg (see /home/johannes/src/xfstests-dev/results//btrfs/001.dmesg)
- output mismatch (see /home/johannes/src/xfstests-dev/results//btrfs/001.out.bad)
    --- tests/btrfs/001.out     2020-01-07 15:49:53.000000000 +0000
    +++ /home/johannes/src/xfstests-dev/results//btrfs/001.out.bad      2020-11-05 16:17:37.266632915 +0000
    @@ -3,38 +3,29 @@
     List root dir
     foo
     Creating snapshot of root dir
    +ERROR: cannot snapshot '/mnt/scratch': No such file or directory
     Create a snapshot of 'SCRATCH_MNT' in 'SCRATCH_MNT/snap'
     List root dir after snapshot
    -foo
    ...
    (Run 'diff -u /home/johannes/src/xfstests-dev/tests/btrfs/001.out /home/johannes/src/xfstests-dev/results//btrfs/001.out.bad'  to see the entire diff)

[2]
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e896dd564434..e1bf3b561b45 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1013,7 +1013,11 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 void btrfs_clean_tree_block(struct extent_buffer *buf)
 {
        struct btrfs_fs_info *fs_info = buf->fs_info;
-       if (btrfs_header_generation(buf) ==
+
+       if (btrfs_is_zoned(fs_info)) {
+               memzero_extent_buffer(buf, 0, buf->len);
+               set_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags);
+       } else if (btrfs_header_generation(buf) ==
            fs_info->running_transaction->transid) {
                btrfs_assert_tree_locked(buf);
 
@@ -4639,8 +4643,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
                                     EXTENT_DIRTY);
        btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
 
-       btrfs_free_redirty_list(cur_trans);
-
        cur_trans->state =TRANS_STATE_COMPLETED;
        wake_up(&cur_trans->commit_wait);
 }
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bfd7f3082037..f9f9c329fa69 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3432,15 +3432,23 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
                pin = old_ref_mod >= 0 && new_ref_mod < 0;
        }
 
+       if (btrfs_is_zoned(fs_info)) {
+               struct btrfs_block_group *cache;
+
+               cache = btrfs_lookup_block_group(fs_info, buf->start);
+               pin_down_extent(trans, cache, buf->start, buf->len, 1);
+               btrfs_put_block_group(cache);
+               pin = 0;
+               goto out;
+       }
+
        if (last_ref && btrfs_header_generation(buf) == trans->transid) {
                struct btrfs_block_group *cache;
 
                if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
                        ret = check_ref_cleanup(trans, buf->start);
-                       if (!ret) {
-                               btrfs_redirty_list_add(trans->transaction, buf);
+                       if (!ret)
                                goto out;
-                       }
                }
 
                pin = 0;
@@ -3452,13 +3460,6 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
                        goto out;
                }
 
-               if (btrfs_is_zoned(fs_info)) {
-                       btrfs_redirty_list_add(trans->transaction, buf);
-                       pin_down_extent(trans, cache, buf->start, buf->len, 1);
-                       btrfs_put_block_group(cache);
-                       goto out;
-               }
-
                WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
 
                btrfs_add_free_space(cache, buf->start, buf->len);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index a8561536cd0d..4acc96969959 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2348,13 +2348,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
                goto scrub_continue;
        }
 
-       /*
-        * At this point, we should have written all the tree blocks
-        * allocated in this transaction. So it's now safe to free the
-        * redirtyied extent buffers.
-        */
-       btrfs_free_redirty_list(cur_trans);
-
        ret = write_all_supers(fs_info, 0);
        /*
         * the super is written, we can safely allow the tree-loggers
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 15f9e8a461ee..e91bdfbb03da 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2763,8 +2763,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
                                                free_extent_buffer(next);
                                                return ret;
                                        }
-                                       btrfs_redirty_list_add(
-                                               trans->transaction, next);
                                } else {
                                        if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
                                                clear_extent_buffer_dirty(next);
@@ -3313,8 +3311,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
                          EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
        extent_io_tree_release(&log->log_csum_range);
 
-       if (trans && log->node)
-               btrfs_redirty_list_add(trans->transaction, log->node);
        btrfs_put_root(log);
 }
 
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 5b61500a0aa9..3140c39d3728 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -42,9 +42,6 @@ int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size);
 int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache);
 void btrfs_calc_zone_unusable(struct btrfs_block_group *cache);
-void btrfs_redirty_list_add(struct btrfs_transaction *trans,
-                           struct extent_buffer *eb);
-void btrfs_free_redirty_list(struct btrfs_transaction *trans);
 void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset,
                                 struct bio *bio);
 void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered);
@@ -137,10 +134,6 @@ static inline int btrfs_load_block_group_zone_info(
 
 static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { }
 
-static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans,
-                                         struct extent_buffer *eb) { }
-static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { }
-
 static inline void btrfs_record_physical_zoned(struct inode *inode,
                                               u64 file_offset, struct bio *bio)
 {